Microsoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMa (analyticsindiamag.com)
I wonder if higher quality datasets are the future rather than using tons of internet scraped texts. Either way, neat model!
![](https://kbin.cafe/media/cache/resolve/entry_thumb/f3/14/f3143d62ec5a7437c5728535239e2e84a2b1838531b98a11332a679e4f2035d7.jpg)
I wonder if higher quality datasets are the future rather than using tons of internet scraped texts. Either way, neat model!
cross-posted from: lemmy.world/post/422633...